• Corpus ID: 219531127

AdaLAM: Revisiting Handcrafted Outlier Detection

  title={AdaLAM: Revisiting Handcrafted Outlier Detection},
  author={Luca Cavalli and Viktor Larsson and Martin R. Oswald and Torsten Sattler and Marc Pollefeys},
Local feature matching is a critical component of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision, and a wide range of approaches have been proposed over the last decades. In this paper we revisit handcrafted approaches to outlier filtering. Based on… 

Figures and Tables from this paper

PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency

PointDSC is presented, a novel deep neural network that explicitly incorporates spatial consistency for pruning outlier correspondences and outperforms the state-of-the-art hand- crafted and learning-based outlier rejection approaches on several real-world datasets by a significant margin.

HarrisZ$^+$: Harris Corner Selection for Next-Gen Image Matching Pipelines

A Stricter Constraint Produces Outstanding Matching: Learning More Reliable Image Matching Using a Quadratic Hinge Triplet Loss Network*

This paper proposes an end-toend image matching method that with less training data to obtain a more accurate and robust performance and strengthens the matching constraints by proposing a novel quadratic hinge triplet (QHT) loss function to improve the network.

Registration of 3D Point Clouds with Low Overlap Master Thesis

Point cloud registration serves as a key component to a wide range of applications include 3D reconstruction and LiDAR odometry and mapping. Existing approaches focus on registration of point clouds

Robust Image Retrieval-based Visual Localization using Kapture

This paper presents kapture, a flexible data format and processing pipeline for structure from motion and visual localization that is released open source that is based on robust image retrieval for coarse camera pose estimation and robust local features for accurate pose refinement.

ULMR: An Unsupervised Learning Framework for Mismatch Removal

Unsupervised learning for mismatch removal (ULMR) is proposed, which shows greater stability, better accuracy, and higher quality in application experiments, demonstrating reduced sampling times and higher compatibility with other classification networks in ablation experiments, indicating its great potential for further use.

MS2DG-Net: Progressive Correspondence Learning via Multiple Sparse Semantics Dynamic Graph

Multiple Sparse Semantics Dynamic Graph Network (MS2 DG-Net) is proposed, in this paper, to predict probabilities of correspondences as inliers and recover camera poses, and outperforms state-of-the-art methods in outlier removal and camera pose estimation tasks on the public datasets with heavy outliers.

Learnable Motion Coherence for Correspondence Pruning

A novel formulation of fitting coherent motions with a smooth function on a graph of correspondences is proposed and it is shown that this formulation allows a closed-form solution by graph Laplacian.

Large Aerial Image Tie Point Matching in Real and Difficult Survey Areas via Deep Learning Method

Image tie point matching is an essential task in real aerial photogrammetry, especially for model tie points. In current photogrammetry production, SIFT is still the main matching algorithm because

An improved 3D human model reconstruction technique based on Cascade MVSNet

A multi-view-based 3D reconstruction method of the human body model is improved, which effectively improves the capability of feature point extraction and matching, enhances the accuracy of the generated human dense point clouds.



GMS: Grid-Based Motion Statistics for Fast, Ultra-robust Feature Correspondence

GMS is proposed, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation and integrates into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement.

Image Matching Across Wide Baselines: From Paper to Practice

It is shown that with proper settings, classical solutions may still outperform the perceived state of the art, and the conducted experiments reveal unexpected properties of structure from motion pipelines that can help improve their performance, for both algorithmic and learned methods.

R2D2: Repeatable and Reliable Detector and Descriptor

This work argues that salient regions are not necessarily discriminative, and therefore can harm the performance of the description, and proposes to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.

Neighbourhood Consensus Networks

An end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model is developed.

From Coarse to Fine: Robust Hierarchical Localization at Large Scale

HF-Net is proposed, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization and sets a new state-of-the-art on two challenging benchmarks for large-scale localization.

Learning to Find Good Correspondences

A novel normalization technique, called Context Normalization, is introduced, which allows the network to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences.

SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter

A RansAC extension that is several orders of magnitude faster than standard RANSAC and as fast as and more robust to degenerate configurations than PROSAC, the currently fastest RANSac extension from the literature is proposed.

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

This work proposes an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector, and shows that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations.

Image Retrieval for Image-Based Localization Revisited

It is shown that retrieval methods using a selective voting scheme are able to outperform state-of-the-art direct matching methods and how both selective voting and correspondence computation can be accelerated by using a Hamming embedding of feature descriptors.

Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions

This paper introduces the first benchmark datasets specifically designed for analyzing the impact of day-night changes, weather and seasonal variations, as well as sequence-based localization approaches and the need for better local features on visual localization.